Image Captioning with Visual Positional Embedding and Bi-linear Pooling.
Sidharth NairPrithwijit GuhaPublished in: CVIP (1) (2023)
Keyphrases
- visual perception
- low level
- image data
- single image
- input image
- image features
- image content
- visually similar
- web images
- spatial information
- image analysis
- visual appearance
- visual cues
- edge detection
- image collections
- visual data
- image representation
- visual features
- feature points
- image retrieval
- similarity measure
- image segmentation
- human observers
- spatial filters
- image regions
- segmentation method
- high resolution
- multiscale
- image set
- business intelligence
- segmentation algorithm
- image classification
- computer vision